VPDR improves the privacy-utility trade-off in ProtoPFL by allocating less noise to high-variance discriminative prototype dimensions via VPP and using DCR to keep feature norms near the clipping threshold without harming predictions.
Effects of degra- dations on deep neural network architectures
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Proposes JFPD with uncertainty and semantic trust weighting for reliable domain adaptation under distribution shift.
citing papers explorer
-
Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning
VPDR improves the privacy-utility trade-off in ProtoPFL by allocating less noise to high-variance discriminative prototype dimensions via VPP and using DCR to keep feature norms near the clipping threshold without harming predictions.
-
Trust-Aware Joint Feature-Prediction Discrepancy for Robust Domain Adaptation
Proposes JFPD with uncertainty and semantic trust weighting for reliable domain adaptation under distribution shift.